Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3403 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2702. Min Range: -8.2702
Max Act: 8.2702. Min Act: -0.1700
Data Index: 6542131 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2702. Min Range: -8.2702
Max Act: 8.0202. Min Act: -0.1700
Data Index: 834544 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2702. Min Range: -8.2702
Max Act: 8.0202. Min Act: -0.1700
Data Index: 4118205 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.8952. Min Act: -0.1700
Data Index: 3358895 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.8952. Min Act: -0.1700
Data Index: 6634569 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.8952. Min Act: -0.1700
Data Index: 4695569 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.8327. Min Act: -0.1700
Data Index: 3546549 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.8327. Min Act: -0.1700
Data Index: 893307 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.8327. Min Act: -0.1700
Data Index: 6758167 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.8327. Min Act: -0.1700
Data Index: 8228461 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 2315361 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 3122670 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 680124 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 1834343 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 7640592 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 6863911 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 2929757 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 6724260 (Open Web Text)
Max Activating Token Index: 958
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 3458807 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2702. Min Range: -8.2702
Max Act: 7.7702. Min Act: -0.1700
Data Index: 2244598 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #19